Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs)

Jing Wang; C. L.Philip Chen; Chi-Hsu Wang

doi:10.1109/ICSSE.2012.6257164

Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs)

Jing Wang^*, C. L.Philip Chen, Chi-Hsu Wang

^*Corresponding author for this work

Department of Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, BP training algorithm is derived. To improve convergent rate, a new method to find near optimal learning rates for FFNN is proposed. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation results show satisfactory results. Finding near optimal learning rates for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing,..., etc.

Original language	English
Title of host publication	Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012
Pages	137-142
Number of pages	6
DOIs	https://doi.org/10.1109/ICSSE.2012.6257164
State	Published - 1 Oct 2012
Event	2012 International Conference on System Science and Engineering, ICSSE 2012 - Dalian, Liaoning, China Duration: 30 Jun 2012 → 2 Jul 2012

Publication series

Name	Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012

Conference

Conference	2012 International Conference on System Science and Engineering, ICSSE 2012
Country	China
City	Dalian, Liaoning
Period	30/06/12 → 2/07/12

Keywords

Back Propagations
Fuzzy Logic
Fuzzy Neural Networks
Gradient Descent
Neural Networks
Optimal training

Access to Document

10.1109/ICSSE.2012.6257164

Fingerprint Dive into the research topics of 'Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs)'. Together they form a unique fingerprint.

Cite this

Wang, J., Chen, C. L. P., & Wang, C-H. (2012). Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs). In Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012 (pp. 137-142). [6257164] (Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012). https://doi.org/10.1109/ICSSE.2012.6257164

Wang, Jing ; Chen, C. L.Philip ; Wang, Chi-Hsu. / Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs). Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012. 2012. pp. 137-142 (Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012).

@inproceedings{b38795f72dec40c4871c085b70c7a209,

title = "Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs)",

abstract = "In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, BP training algorithm is derived. To improve convergent rate, a new method to find near optimal learning rates for FFNN is proposed. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation results show satisfactory results. Finding near optimal learning rates for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing,..., etc.",

keywords = "Back Propagations, Fuzzy Logic, Fuzzy Neural Networks, Gradient Descent, Neural Networks, Optimal training",

author = "Jing Wang and Chen, {C. L.Philip} and Chi-Hsu Wang",

year = "2012",

month = oct,

day = "1",

doi = "10.1109/ICSSE.2012.6257164",

language = "English",

isbn = "9781467309455",

series = "Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012",

pages = "137--142",

booktitle = "Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012",

note = "null ; Conference date: 30-06-2012 Through 02-07-2012",

}

Wang, J, Chen, CLP & Wang, C-H 2012, Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs). in Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012., 6257164, Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012, pp. 137-142, 2012 International Conference on System Science and Engineering, ICSSE 2012, Dalian, Liaoning, China, 30/06/12. https://doi.org/10.1109/ICSSE.2012.6257164

Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs). / Wang, Jing; Chen, C. L.Philip; Wang, Chi-Hsu.

Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012. 2012. p. 137-142 6257164 (Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs)

AU - Wang, Jing

AU - Chen, C. L.Philip

AU - Wang, Chi-Hsu

PY - 2012/10/1

Y1 - 2012/10/1

N2 - In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, BP training algorithm is derived. To improve convergent rate, a new method to find near optimal learning rates for FFNN is proposed. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation results show satisfactory results. Finding near optimal learning rates for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing,..., etc.

AB - In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, BP training algorithm is derived. To improve convergent rate, a new method to find near optimal learning rates for FFNN is proposed. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation results show satisfactory results. Finding near optimal learning rates for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing,..., etc.

KW - Back Propagations

KW - Fuzzy Logic

KW - Fuzzy Neural Networks

KW - Gradient Descent

KW - Neural Networks

KW - Optimal training

UR - http://www.scopus.com/inward/record.url?scp=84866658670&partnerID=8YFLogxK

U2 - 10.1109/ICSSE.2012.6257164

DO - 10.1109/ICSSE.2012.6257164

M3 - Conference contribution

AN - SCOPUS:84866658670

SN - 9781467309455

T3 - Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012

SP - 137

EP - 142

BT - Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012

Y2 - 30 June 2012 through 2 July 2012

ER -

Wang J, Chen CLP, Wang C-H. Finding the near optimal learning rates of Fuzzy Neural Networks (FNNs) via its equivalent fully connected neural networks (FFNNs). In Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012. 2012. p. 137-142. 6257164. (Proceedings 2012 International Conference on System Science and Engineering, ICSSE 2012). https://doi.org/10.1109/ICSSE.2012.6257164